Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron fires on programming‐language syntax—particularly assignment, method‐call, and bracket tokens in code snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     animated
    -0.08
    widget
    -0.07
    WRITE
    -0.07
     seizing
    -0.07
     đáo
    -0.07
     trailers
    -0.06
    configure
    -0.06
     eggs
    -0.06
     Beer
    -0.06
     joys
    -0.06
    POSITIVE LOGITS
    LOOK
    0.06
    _slow
    0.06
    ①
    0.06
    ционный
    0.06
    insurance
    0.06
     texas
    0.06
    anten
    0.06
     anchor
    0.06
     vừa
    0.06
    _sd
    0.06
    Act Density 0.099%

    No Known Activations